INDEX

Explanations

references to scientific publications and numerical data

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ð²Ð¸Ð¶

-0.16

 Manuals

-0.16

Ã±ana

-0.14

mtree

-0.14

Lar

-0.14

oÅĽci

-0.14

argar

-0.14

cerer

-0.13

Ø¬Ø§Ø±

-0.13

iky

-0.13

POSITIVE LOGITS

 article

0.21

 Article

0.20

 Articles

0.18

-article

0.18

 articles

0.18

Article

0.18

 ÙħÙĤØ§ÙĦÙĩ

0.17

eer

0.17

_article

0.17

Articles

0.17

Activations Density 0.220%

references to scientific publications and numerical data

No Comments

No Known Activations